Synthetic Power Analyses: Empirical Evaluation and Application to Cognitive Neuroimaging
This work addresses sample size determination for researchers in cognitive neuroimaging, offering a potentially cheaper method, but it is incremental as it builds on existing power analysis concepts with a new application.
The authors tackled the problem of costly traditional power analyses for sample size selection in cognitive neuroscience by proposing synthetic power analyses, which use synthesized brain imaging data from an implicit generative model, and found it could be a low-cost alternative to pilot data collection when experiments share cognitive processes with prior ones.
In the experimental sciences, statistical power analyses are often used before data collection to determine the required sample size. However, traditional power analyses can be costly when data are difficult or expensive to collect. We propose synthetic power analyses; a framework for estimating statistical power at various sample sizes, and empirically explore the performance of synthetic power analysis for sample size selection in cognitive neuroscience experiments. To this end, brain imaging data is synthesized using an implicit generative model conditioned on observed cognitive processes. Further, we propose a simple procedure to modify the statistical tests which result in conservative statistics. Our empirical results suggest that synthetic power analysis could be a low-cost alternative to pilot data collection when the proposed experiments share cognitive processes with previously conducted experiments.